INDEX

Explanations

references to biblical figures and narratives

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸°

-0.16

ectl

-0.15

uru

-0.15

stÃ¥

-0.14

æ¯

-0.14

 Nikola

-0.14

etas

-0.14

IRM

-0.14

 Norton

-0.14

POSITIVE LOGITS

 Joseph

0.26

 Egyptian

0.24

Joseph

0.23

 Egypt

0.21

Ph

0.21

 jose

0.21

 Egyptians

0.21

dream

0.20

 Dreams

0.20

 dreams

0.19

Activations Density 0.007%

references to biblical figures and narratives

No Comments

No Known Activations